Classifying documents at scale with few examples
A post published on September 10, 2026 describes labeling 200 examples with an agent and classifying 191,724 documents for about US$0.70 in inference compute.
Source: Como Criar um Classificador de Documentos com Agents e SetFit (danielvanstrien.xyz). Text prepared with AI from this source.
What happened and what to do
The post, published on September 10, 2026, describes using an agent to label 200 examples and train a document-purpose classifier with SetFit. The model classified 191,724 documents from the FinePDFs-Edu dataset for about US$0.70 in inference compute, illustrating a way to reduce the cost of large-scale data curation.
A company could apply this pattern to its own document collections: define categories, review a labeled sample, measure classifier quality, and automate triage while routing uncertain cases to human review. The workflow could include collection, monitoring, decision logging, and periodic model updates.
How the consultancy can help
Wendelmaques can diagnose the document collection, classification criteria, and security requirements; define an implementation scope; and build and operate the triage, evaluation, and monitoring workflow on the company’s infrastructure.
Next step
Send a short description of your document collection and desired classification process to receive a scoped proposal.
Let's assess your project
I reply with scope and a proposal.